Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43888
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols, particularly diacritics and accent marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Â
    -0.09
     â
    -0.08
    ÂĹ
    -0.08
    ÂĿ
    -0.08
    Âħ
    -0.08
     —
    -0.07
    ÂĦ
    -0.07
     ÂŃ
    -0.07
     (“
    -0.06
    ÃĤ
    -0.06
    POSITIVE LOGITS
     county
    0.20
     County
    0.18
     COUNTY
    0.18
    county
    0.18
    County
    0.18
     commissioners
    0.16
     Commissioners
    0.15
    åİ¿
    0.14
     counties
    0.14
     commissioner
    0.13
    Activations Density 0.001%

    No Known Activations